I'm especially interested in how this can be applied to the world of the game. I think that creates much more interesting results than NPCs who can hold dynamic conversation. Imagine an MMO where quests you complete actually shape the world (its landscape, structures and enemies). Then dynamic quests can be created based on the new world, creating a living loop.
> A tool is not meant to be the object of our attention; rather the tool should reveal the true object of our attention (the thing the tool acts upon), rather than obscuring it
I think this is true of AI agents. What is the object of our engineering attention? Applications, features, defect resolution. Not code.
Author here: yeah, this is a good point and something I think about even outside the context of agentic coding.
I've also tinkered with this idea myself in the context of prompt engineering with my Grace Browser project (https://trygrace.dev/), which converts code to an equivalent dynamic web form live within your browser.
I do think it's useful to remember that code is not the end goal and is itself just another mediated interface to the actual goal: the product your building. However, I think even if you cut code out of the picture the chat interface is still not necessarily the right interface for building a product. A great example of how to build a non-chat interface to product building (predating the AI boom) is Bret Victor's Inventing on Principle talk (https://www.youtube.com/watch?v=PUv66718DII) and there might be ways we can refresh the ideas in that talk for the AI era (although I still don't have any specific thoughts along those lines yet).
Totally agree about the chat interface. I like to say it’s “infinitely powerful and infinitely confusing.” A dangerous combination. And, arguing with myself, I think it’s fair to say the code is AN object of our attention, if not THE object. A common metaphor being applied to agentic coding is the invention of power tools. If AI is the drill, and the goal is a house, then the code is the framing.
They have a monolith but struggle with individual subsystem failures bringing down the whole thing. Sounds like they would benefit from Elixir’s isolated, fail-fast architecture.
> I was being exposed to engineering concepts that just weren't a thing in agency work: unit testing, CI/CD, git hygiene, release management.
As someone who’s worked at an agency that’s grown from twenty engineers to hundreds over the last five years, what? Even when we were small and scrappy we still wrote unit tests…
My experience was 100% different (but also 6+ years ago). Margins just weren't enough to build it into estimates and it was nearly impossible to sell it to clients as a line item.
“Tending bar” puts more emphasis on what one might argue is the more important part of the phrase. No one is there for the tender. Consider versus “woodworking”: you want the work, not the hunk of wood.
We need a publicly funded body whose purpose is to issue grants for firms to reproduce scientific findings. A scientific reproduction corps. Extra can be awarded for finding flawed/fraudulent research. This would create a community of organizations that counter-balance industry incentives and instill trust in our scientific process.
